© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78484
    Prev
    Next
    INDEX
    Explanations

    Django configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decisões
    -0.08
    価格
    -0.08
    _upper
    -0.08
     règles
    -0.08
     গুরু
    -0.07
    _limits
    -0.07
     Estimates
    -0.07
     elämä
    -0.07
    _prices
    -0.07
     strike
    -0.07
    POSITIVE LOGITS
     hybr
    0.08
     Evo
    0.08
     lombok
    0.08
     listado
    0.08
    Comp
    0.08
     bekannten
    0.08
    Listed
    0.08
     Aber
    0.08
     conhecidos
    0.07
     híbr
    0.07
    Activations Density 0.001%

    No Known Activations